Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Sonix API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fsonix.ai%2Fsonix-api" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fsonix.ai%2Fsonix-api" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Sonix API.
Submit new media
List media files
Get media status
Update media
GET STARTED
For Agents
Programmatically submit new media, list media files. Covers 23 operations with bearer authentication.
Use for: I need to submit new media, I want to media files, Search for media status, Find all media
Not supported: Does not handle payments, communications, or crm - use for ai and machine learning only.
API for automated transcription, translation, and subtitle creation for audio and video files. The API exposes 23 endpoints secured with bearer authentication.
Delete media
Patterns agents use Sonix API for, with concrete tasks.
★ AI and Machine Learning Operations
Use the Sonix API to perform ai ml operations programmatically. The API provides 23 endpoints covering core functionality including submit new media, list media files, get media status.
Call POST /media to submit new media
Automated folders Management
Automate folders operations by combining multiple Sonix API endpoints. Agents can list media files and then get media status in a single workflow.
Call GET /media to list media files, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Sonix API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle bearer tokens manually.
Search Jentic for 'submit new media', load the operation schema, and execute with Jentic-managed credentials
23 endpoints — api for automated transcription, translation, and subtitle creation for audio and video files.
METHOD
PATH
DESCRIPTION
/media
Submit new media
/media
List media files
/media/{id}
Get media status
/media/{id}
Update media
/media/{id}
Delete media
/media/{id}/transcript
Get transcript
/media/{id}/transcript
Update transcript
/media/{id}/transcript/split
Split transcript into subtitles
/media
Submit new media
/media
List media files
/media/{id}
Get media status
/media/{id}
Update media
/media/{id}
Delete media
/media/{id}/transcript
Get transcript
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Sonix API by hand means setting up its bearer auth, pointing at the api.sonix.ai/v1 host, and handling media upload and transcript editing plus retries yourself. Through Jentic you install once, import the Sonix API from the API Directory, store the token once, and your agent calls it.
Permission scoping
The Sonix API puts the media id in the URL path (/media/{id}, /media/{id}/transcript/split), so a rule can pin your agent to one media file: it can read and edit that file's transcript and nothing else. You choose the operations it may call, so destructive ones like deleting media are not included unless you add them.
Credential isolation
Your Sonix token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'submit new media' or 'edit a transcript', and Jentic returns the matching Sonix API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Sonix API through Jentic.
What authentication does the Sonix API use?
The Sonix API uses a Bearer token in the Authorization header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I submit new media with the Sonix API?
Yes. Use the POST /media endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Sonix API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I submit new media through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'submit new media'. Jentic returns the matching Sonix API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Sonix API have?
The Sonix API exposes 23 endpoints covering folders, media, summarizations operations.
Can I limit what my agent is allowed to do with the Sonix API?
Yes. Because Jentic One runs self-hosted on your own infrastructure, you write the rules that decide which Sonix API operations and credentials the agent may use. Since the Sonix API carries the media id in the URL path (for example /media/{id} and /media/{id}/transcript/split), a rule can pin the agent to a single media file so it only reads and edits that file's transcript and nothing else. You also choose the exact operations it may call, so destructive ones such as DELETE /media/{id} stay out of reach unless you explicitly grant them.
/media/{id}/transcript
Update transcript
/media/{id}/transcript/split
Split transcript into subtitles